Get Started  ·  FIVE STEPS, ALL LOCAL

From Clone ToFirst Session.

The repos are private until the public beta in Q4 2026. The steps below are exactly what will unlock then, everything runs locally, no account, no API key, no credit card.

◉
SOURCE ACCESS, COMING SOON · Q4 2026

Anvaya CLI and Anvaya Mind are private repositories until the public beta. Join the early-access list and we’ll send you the clone-and-build instructions the moment they’re public.

No spam. Early access only. Unsubscribe anytime.✓ You’re on the list. We’ll email you at launch.Enter a valid email address.
01

Prerequisites

Rust 1.75 or newer, and Ollama running locally with at least one model pulled. Ollama is what lets Anvaya run without an API key.

TERMINAL, STEP 01
# Rust toolchain, https://rustup.rs
$rustc --version
rustc 1.75.0 or newer
# Pull a coding model
$ollama pull devstral:latest
02

Build the CLI

Anvaya is not on crates.io or Homebrew yet, you build it from source. The release profile produces a single ~12.1MB binary with no runtime dependencies.

TERMINAL, STEP 02
$git clone https://github.com/NaMan6122/Anvaya-CLI.git
$cd Anvaya-CLI
$cargo build --release
# Binary at target/release/anv
03

Install & initialize

Put anv on your PATH, then initialize the project you want it to work in. anv init creates the .anvaya/ directory that holds config, sessions, and backups.

TERMINAL, STEP 03
$cargo install --path crates/anv
$cd ~/code/your-project
$anv init
✓ .anvaya/ initialized
04

First session

Launch the TUI, or skip it entirely and run headless. Keys 1-7 switch panels, Tab cycles, Y/N approves.

TERMINAL, STEP 04
$anv
# or headless, for pipes and CI
$anv --no-tui --plan-only "what would change to add Redis caching?"
$anv --continue
05

Add Mind

Mind is a separate daemon. It creates .anvaya/mind/ inside your project, holds an exclusive lock, and runs six background workers that keep the graph consolidated.

TERMINAL, STEP 05
$git clone https://github.com/NaMan6122/anvaya-mind-rs.git
$cd anvaya-mind-rs && cargo build --release
# Produces mind-daemon and mind-mcp
$mind-daemon --project ~/code/your-project

Already Using Claude Code?

Keep Your Tool. Add The Memory.

Mind ships an MCP server, so it attaches to any MCP-capable client without replacing it. Drop this in your project root and Mind becomes available as a set of tools inside the editor or agent you already use.

.mcp.jsonproject root
# .mcp.json, in your project root
{
  "mcpServers": {
    "anvaya-mind": {
      "command": "mind-mcp",
      "args": ["--project", "."]
    }
  }
}

That exposes eight tools, mind_query, mind_search, mind_record_change, mind_get_node, mind_stats, mind_start_session, mind_end_session, mind_get_threads. mind_query returns a packed context under a token budget you set, defaulting to 4,096.